© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40198
    Prev
    Next
    INDEX
    Explanations

    code snippets and file names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens (pure digit sequences or numbers) rather than words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ständig
    -1.02
     réflé
    -1.02
    acheter
    -0.98
     schwä
    -0.97
     perpé
    -0.93
    jupiter
    -0.93
    バッグ
    -0.90
     déploy
    -0.90
    schuhe
    -0.89
     häufig
    -0.88
    POSITIVE LOGITS
     tambin
    1.10
     đọc
    1.04
    CESO
    1.02
    过来了
    1.01
     Deine
    0.98
     einer
    0.98
    äne
    0.97
    他已经
    0.96
    /*++
    0.95
     exalt
    0.94
    Activations Density 0.014%

    No Known Activations